@phdthesis{Hoerdegen2005,
  author    = {H{\"o}rdegen, Simone},
  title     = {{\"U}berlegungen zu einer sich selbst steuernden Wirbelschichtanlage},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-15166},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2005},
  abstract  = {Eines der gr{\"o}ßten Probleme bei Granulationsprozessen in der pharmazeutischen Industrie ist die Feuchtigkeit der Prozessluft. Kann bzw. m{\"o}chte man die Luft aus {\"o}konomischen oder sonstigen Gr{\"u}nden hinsichtlich ihres absoluten Feuchtgehalts nicht konditionieren, bleibt bei hoher Luftfeuchte - wie sie z.B. beim Aufzug eines Gewitters oder bei heftigen Regenf{\"a}llen auftritt - oft nur die Option des Produktionsstillstandes. Die vorliegende Arbeit befasst sich einerseits mit der Frage, ob es m{\"o}glich ist, unabh{\"a}ngig von den Außenluftbedingungen - wie Temperatur, Druck und relative Feuchte - Granulate mit vergleichbaren Eigenschaften zu reproduzieren. Zum anderen soll gekl{\"a}rt werden, welchen Einfluss verschiedene Prozess- und Materialparameter bzw. deren Schwankungen auf das Endprodukt haben, und was dies wiederum f{\"u}r eine Automatisierung des Prozesses bzw. f{\"u}r die Anforderungen an eine Steuer- und Regelung der Herstellanlage bedeutet. Ausgehend von der Massenbilanzierung einer Wirbelschichtgranulierung wird der Einfluss verschiedener Prozess- und Materialparameter auf ein Standardgranulat untersucht. Die Ergebnisse der unterschiedlichen Versuchsreihen best{\"a}tigen einerseits die Reproduzierbarkeit von Granulateigenschaften basierend auf den Berechnungen der kritischen Spr{\"u}hrate. Andererseits zeigen sie den Einfluss verschiedener Prozess- und Materialparameter auf die Qualit{\"a}t des Endproduktes. Hieraus k{\"o}nnen wichtige Erkenntnisse f{\"u}r eine automatische Steuer- und Regelung der Herstellanlage abgeleitet und entsprechende Sollanforderungen f{\"u}r jeden einzelnen Prozessparameter sowie die {\"u}berwachenden Sensoren definiert werden. Die Berechnungen zur Machbarkeit eines Granulatansatzes sind eine wertvolle Entscheidungsgrundlage hinsichtlich der Planung einer Granulatherstellung und dienen auch f{\"u}r eine Ansatzvergr{\"o}ßerung als Kalkulationsbasis. Ebenso kann die Algorithmenabfolge der „kritischen Spr{\"u}hrate" zusammen mit den Formeln der „Berechnungen zur Machbarkeit" f{\"u}r die Anpassung der Prozessparameter an die jahres- und tageszeitlichen Schwankungen der Außenluft herangezogen werden. Wie theoretische Studien zum „Ausgleich der Außenluftbedingungen" aufzeigen, ist es mit Hilfe dieser Algorithmen m{\"o}glich, die freie Feuchte w{\"a}hrend der Spr{\"u}hphase auf ein definiertes Niveau zu bringen und dort zu halten. Dieser Anteil an {\"u}bersch{\"u}ssigem Wasser ist prim{\"a}r f{\"u}r das Kornwachstum und somit f{\"u}r die Reproduktion von Granulaten verantwortlich. Die vorliegende Arbeit stellt mit ihren theoretischen Ans{\"a}tzen einen entscheidenden Schritt hin zu einer automatisierten Wirbelschichtanlage dar. Sie zeigt Ansatzpunkte f{\"u}r ein m{\"o}gliches Vorgehen auf und liefert Hinweise f{\"u}r die Anforderungen an Messsensoren sowie Steuer- und Regeleinheiten.},
  subject      = {Wirbelschichtverfahren},
  language  = {de}
}
@article{HaeusnerHerbstBittorfetal.2021,
  author    = {Haeusner, Sebastian and Herbst, Laura and Bittorf, Patrick and Schwarz, Thomas and Henze, Chris and Mauermann, Marc and Ochs, Jelena and Schmitt, Robert and Blache, Ulrich and Wixmerten, Anke and Miot, Sylvie and Martin, Ivan and Pullig, Oliver},
  title     = {From Single Batch to Mass Production-Automated Platform Design Concept for a Phase II Clinical Trial Tissue Engineered Cartilage Product},
  series = {Frontiers in Medicine},
  volume    = {8},
  journal   = {Frontiers in Medicine},
  issn      = {2296-858X},
  doi       = {10.3389/fmed.2021.712917},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-244631},
  year      = {2021},
  abstract  = {Advanced Therapy Medicinal Products (ATMP) provide promising treatment options particularly for unmet clinical needs, such as progressive and chronic diseases where currently no satisfying treatment exists. Especially from the ATMP subclass of Tissue Engineered Products (TEPs), only a few have yet been translated from an academic setting to clinic and beyond. A reason for low numbers of TEPs in current clinical trials and one main key hurdle for TEPs is the cost and labor-intensive manufacturing process. Manual production steps require experienced personnel, are challenging to standardize and to scale up. Automated manufacturing has the potential to overcome these challenges, toward an increasing cost-effectiveness. One major obstacle for automation is the control and risk prevention of cross contaminations, especially when handling parallel production lines of different patient material. These critical steps necessitate validated effective and efficient cleaning procedures in an automated system. In this perspective, possible technologies, concepts and solutions to existing ATMP manufacturing hurdles are discussed on the example of a late clinical phase II trial TEP. In compliance to Good Manufacturing Practice (GMP) guidelines, we propose a dual arm robot based isolator approach. Our novel concept enables complete process automation for adherent cell culture, and the translation of all manual process steps with standard laboratory equipment. Moreover, we discuss novel solutions for automated cleaning, without the need for human intervention. Consequently, our automation concept offers the unique chance to scale up production while becoming more cost-effective, which will ultimately increase TEP availability to a broader number of patients.},
  language  = {en}
}
@article{KrenzerMakowskiHekaloetal.2022,
  author    = {Krenzer, Adrian and Makowski, Kevin and Hekalo, Amar and Fitting, Daniel and Troya, Joel and Zoller, Wolfram G. and Hann, Alexander and Puppe, Frank},
  title     = {Fast machine learning annotation in the medical domain: a semi-automated video annotation tool for gastroenterologists},
  series = {BioMedical Engineering OnLine},
  volume    = {21},
  journal   = {BioMedical Engineering OnLine},
  number    = {1},
  doi       = {10.1186/s12938-022-01001-x},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-300231},
  year      = {2022},
  abstract  = {Background Machine learning, especially deep learning, is becoming more and more relevant in research and development in the medical domain. For all the supervised deep learning applications, data is the most critical factor in securing successful implementation and sustaining the progress of the machine learning model. Especially gastroenterological data, which often involves endoscopic videos, are cumbersome to annotate. Domain experts are needed to interpret and annotate the videos. To support those domain experts, we generated a framework. With this framework, instead of annotating every frame in the video sequence, experts are just performing key annotations at the beginning and the end of sequences with pathologies, e.g., visible polyps. Subsequently, non-expert annotators supported by machine learning add the missing annotations for the frames in-between. Methods In our framework, an expert reviews the video and annotates a few video frames to verify the object's annotations for the non-expert. In a second step, a non-expert has visual confirmation of the given object and can annotate all following and preceding frames with AI assistance. After the expert has finished, relevant frames will be selected and passed on to an AI model. This information allows the AI model to detect and mark the desired object on all following and preceding frames with an annotation. Therefore, the non-expert can adjust and modify the AI predictions and export the results, which can then be used to train the AI model. Results Using this framework, we were able to reduce workload of domain experts on average by a factor of 20 on our data. This is primarily due to the structure of the framework, which is designed to minimize the workload of the domain expert. Pairing this framework with a state-of-the-art semi-automated AI model enhances the annotation speed further. Through a prospective study with 10 participants, we show that semi-automated annotation using our tool doubles the annotation speed of non-expert annotators compared to a well-known state-of-the-art annotation tool. Conclusion In summary, we introduce a framework for fast expert annotation for gastroenterologists, which reduces the workload of the domain expert considerably while maintaining a very high annotation quality. The framework incorporates a semi-automated annotation system utilizing trained object detection models. The software and framework are open-source.},
  language  = {en}
}
@inproceedings{OPUS4-30171,
  title     = {Digitalization as a challenge for justice and administration},
  editor    = {Ludwigs, Markus and Muriel Ciceri, Jos{\´e} Hern{\´a}n and Velling, Annika},
  publisher = {W{\"u}rzburg University Press},
  address   = {W{\"u}rzburg},
  isbn      = {978-3-95826-200-3},
  issn      = {2941-2854},
  doi       = {10.25972/WUP-978-3-95826-201-0},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-301717},
  pages     = {VIII, 153},
  year      = {2023},
  abstract  = {Digitalization is one of the global challenges for justice and This volume documents the presentations of a multilingual online conference on "Digitalization as a challenge for justice and administration" held in March 2022. The contributions of the international team of authors provide insights into central issues of this highly relevant subject from African, Japanese, U.S., Swiss, Latin American and German perspectives. The result is a multifaceted picture of digitalization in the context of public, private and even criminal law.},
  subject      = {Digitalisierung},
  language  = {mul}
}
@inproceedings{FoerstnerHagedornKoltzenburgetal.2011,
  author    = {F{\"o}rstner, Konrad and Hagedorn, Gregor and Koltzenburg, Claudia and Kubke, Fabiana and Mietchen, Daniel},
  title     = {Collaborative platforms for streamlining workflows in Open Science},
  series = {Proceedings of the 6th Open Knowledge Conference},
  booktitle = {Proceedings of the 6th Open Knowledge Conference},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-101678},
  year      = {2011},
  abstract  = {Despite the internet's dynamic and collaborative nature, scientists continue to produce grant proposals, lab notebooks, data files, conclusions etc. that stay in static formats or are not published online and therefore not always easily accessible to the interested public. Because of limited adoption of tools that seamlessly integrate all aspects of a research project (conception, data generation, data evaluation, peerreviewing and publishing of conclusions), much effort is later spent on reproducing or reformatting individual entities before they can be repurposed independently or as parts of articles. We propose that workflows - performed both individually and collaboratively - could potentially become more efficient if all steps of the research cycle were coherently represented online and the underlying data were formatted, annotated and licensed for reuse. Such a system would accelerate the process of taking projects from conception to publication stages and allow for continuous updating of the data sets and their interpretation as well as their integration into other independent projects. A major advantage of such work ows is the increased transparency, both with respect to the scientific process as to the contribution of each participant. The latter point is important from a perspective of motivation, as it enables the allocation of reputation, which creates incentives for scientists to contribute to projects. Such work ow platforms offering possibilities to fine-tune the accessibility of their content could gradually pave the path from the current static mode of research presentation into a more coherent practice of open science.},
  language  = {en}
}
@article{KrenzerHeilFittingetal.,
  author    = {Krenzer, Adrian and Heil, Stefan and Fitting, Daniel and Matti, Safa and Zoller, Wolfram G. and Hann, Alexander and Puppe, Frank},
  title     = {Automated classification of polyps using deep learning architectures and few-shot learning},
  series = {BMC Medical Imaging},
  volume    = {23},
  journal   = {BMC Medical Imaging},
  doi       = {10.1186/s12880-023-01007-4},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-357465},
  abstract  = {Background Colorectal cancer is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is a colonoscopy. However, not all colon polyps have the risk of becoming cancerous. Therefore, polyps are classified using different classification systems. After the classification, further treatment and procedures are based on the classification of the polyp. Nevertheless, classification is not easy. Therefore, we suggest two novel automated classifications system assisting gastroenterologists in classifying polyps based on the NICE and Paris classification. Methods We build two classification systems. One is classifying polyps based on their shape (Paris). The other classifies polyps based on their texture and surface patterns (NICE). A two-step process for the Paris classification is introduced: First, detecting and cropping the polyp on the image, and secondly, classifying the polyp based on the cropped area with a transformer network. For the NICE classification, we design a few-shot learning algorithm based on the Deep Metric Learning approach. The algorithm creates an embedding space for polyps, which allows classification from a few examples to account for the data scarcity of NICE annotated images in our database. Results For the Paris classification, we achieve an accuracy of 89.35 \%, surpassing all papers in the literature and establishing a new state-of-the-art and baseline accuracy for other publications on a public data set. For the NICE classification, we achieve a competitive accuracy of 81.13 \% and demonstrate thereby the viability of the few-shot learning paradigm in polyp classification in data-scarce environments. Additionally, we show different ablations of the algorithms. Finally, we further elaborate on the explainability of the system by showing heat maps of the neural network explaining neural activations. Conclusion Overall we introduce two polyp classification systems to assist gastroenterologists. We achieve state-of-the-art performance in the Paris classification and demonstrate the viability of the few-shot learning paradigm in the NICE classification, addressing the prevalent data scarcity issues faced in medical machine learning.},
  language  = {en}
}
@article{KrenzerBanckMakowskietal.2023,
  author    = {Krenzer, Adrian and Banck, Michael and Makowski, Kevin and Hekalo, Amar and Fitting, Daniel and Troya, Joel and Sudarevic, Boban and Zoller, Wolfgang G. and Hann, Alexander and Puppe, Frank},
  title     = {A real-time polyp-detection system with clinical application in colonoscopy using deep convolutional neural networks},
  series = {Journal of Imaging},
  volume    = {9},
  journal   = {Journal of Imaging},
  number    = {2},
  issn      = {2313-433X},
  doi       = {10.3390/jimaging9020026},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-304454},
  year      = {2023},
  abstract  = {Colorectal cancer (CRC) is a leading cause of cancer-related deaths worldwide. The best method to prevent CRC is with a colonoscopy. During this procedure, the gastroenterologist searches for polyps. However, there is a potential risk of polyps being missed by the gastroenterologist. Automated detection of polyps helps to assist the gastroenterologist during a colonoscopy. There are already publications examining the problem of polyp detection in the literature. Nevertheless, most of these systems are only used in the research context and are not implemented for clinical application. Therefore, we introduce the first fully open-source automated polyp-detection system scoring best on current benchmark data and implementing it ready for clinical application. To create the polyp-detection system (ENDOMIND-Advanced), we combined our own collected data from different hospitals and practices in Germany with open-source datasets to create a dataset with over 500,000 annotated images. ENDOMIND-Advanced leverages a post-processing technique based on video detection to work in real-time with a stream of images. It is integrated into a prototype ready for application in clinical interventions. We achieve better performance compared to the best system in the literature and score a F1-score of 90.24\% on the open-source CVC-VideoClinicDB benchmark.},
  language  = {en}
}